🤖 AI Summary
During the Russia-Ukraine war, Twitter witnessed intertwined dissemination of open-source intelligence (OSINT) and obfuscatory disinformation—termed “BULLSHINT,” a novel conceptualization introduced in this study. Method: We propose a multimodal analytical framework integrating sentiment analysis, stance detection, misinformation identification, named entity recognition (NER), and community detection to empirically analyze nearly two million tweets from January 2022 to July 2023. We formally define and operationalize BULLSHINT through quantifiable linguistic and behavioral criteria, and examine its propagation in relation to community structure and stance distribution. Contribution/Results: Findings reveal that major military developments significantly amplify negative sentiment; user stances exhibit non-binary, multidimensional distributions; specific actor groups systematically disseminate BULLSHINT; and community structures are deeply entangled with ideological alignment and topic preference—exposing structural vulnerabilities of social platforms in digital cognitive warfare.
📝 Abstract
This paper examines the role of Open Source Intelligence (OSINT) on Twitter regarding the Russo-Ukrainian war, distinguishing between genuine OSINT and deceptive misinformation efforts, termed "BULLSHINT." Utilizing a dataset spanning from January 2022 to July 2023, we analyze nearly 2 million tweets from approximately 1,040 users involved in discussing real-time military engagements, strategic analyses, and misinformation related to the conflict. Using sentiment analysis, partisanship detection, misinformation identification, and Named Entity Recognition (NER), we uncover communicative patterns and dissemination strategies within the OSINT community. Significant findings reveal a predominant negative sentiment influenced by war events, a nuanced distribution of pro-Ukrainian and pro-Russian partisanship, and the potential strategic manipulation of information. Additionally, we apply community detection techniques, which are able to identify distinct clusters partisanship, topics, and misinformation, highlighting the complex dynamics of information spread on social media. This research contributes to the understanding of digital warfare and misinformation dynamics, offering insights into the operationalization of OSINT in geopolitical conflicts.
